GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis

Srikumar Sastry, Subash Khanal, Aayush Dhakal, Nathan Jacobs

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

We present GeoSynth, a model for synthesizing satellite images with global style and image-driven layout control. The global style control is via textual prompts or geographic location. These enable the specification of scene semantics or regional appearance respectively, and can be used together. We train our model on a large dataset of paired satellite imagery, with automatically generated captions, and OpenStreetMap data. We evaluate various combinations of control inputs, including different types of layout controls. Results demonstrate that our model can generate diverse, high-quality images and exhibits excellent zero-shot generalization. The code and model check-points are available at https://github.com/mvrl/GeoSynth.

Original languageEnglish
Title of host publicationProceedings - 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
PublisherIEEE Computer Society
Pages460-470
Number of pages11
ISBN (Electronic)9798350365474
DOIs
StatePublished - 2024
Event2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024 - Seattle, United States
Duration: Jun 16 2024Jun 22 2024

Publication series

NameIEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
ISSN (Print)2160-7508
ISSN (Electronic)2160-7516

Conference

Conference2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, CVPRW 2024
Country/TerritoryUnited States
CitySeattle
Period06/16/2406/22/24

Keywords

  • Control Net
  • Diffusion Models
  • Satellite image generation

Fingerprint

Dive into the research topics of 'GeoSynth: Contextually-Aware High-Resolution Satellite Image Synthesis'. Together they form a unique fingerprint.

Cite this